Stay Confident
Subscribe to our weekly newsletter to stay confident in the AI systems you build.
LLM Arena-as-a-Judge: LLM-Evals for Comparison-Based Regression Testing
Everything you need to run LLM Arena-as-a-judge: a comparison-based, pairwise approach to regression testing LLMs, with DeepEval code to set it up.
Jeffrey Ip
RAG Evaluation Metrics: Assessing Answer Relevancy, Faithfulness, Contextual Relevancy, And More
RAG evaluation metrics — answer relevancy, faithfulness, and contextual relevancy — measure retrieval and generation quality, with working DeepEval code examples.
Jeffrey Ip
LLM Evals Framework That Predicts ROI: A Step-by-Step Guide
Most LLM evals fail because their metrics don't predict ROI. This playbook shows how to build outcome-based evals that correlate with real business KPIs and user value.
Jeffrey Ip
G-Eval Simply Explained: LLM-as-a-Judge for LLM Evaluation
The definitive guide to G-Eval: how this LLM-as-a-judge metric works, chain-of-thought scoring, and how to evaluate LLM apps on custom criteria with DeepEval.
Kritin Vongthongsri
Top LLM Evaluators for Testing LLM Systems at Scale
A rundown of the top LLM evaluators for testing at scale in 2025, from G-Eval and other LLM-as-a-judge metrics to the tooling that runs them in production.
Jeffrey Ip
How I raised Confident AI's $2.2M seed round in 5 days
Confident AI raised an oversubscribed $2.2M seed round in 5 days. Here's the fundraising strategy, the investor conversations, and the hard lessons from the raise.
Jeffrey Ip
How I Built Deterministic LLM Evaluation Metrics for DeepEval
DeepEval's DAG metrics make LLM-as-a-judge scoring deterministic by running outputs through a decision tree. Here's how I built these reliable, explainable metrics.
Jeffrey Ip
LLM Agent Evaluation Metrics in 2026: Tool Calling, Task Completion, Reasoning, and Trace-Based Evals
Learn how to evaluate LLM agents end-to-end with tool calling, task completion, reasoning, trace-based evals, human review, and DeepEval code examples.
Kritin Vongthongsri
LLM Guardrails for Data Leakage, Prompt Injection, and More
LLM guardrails are input and output guards that block data leakage, prompt injection, and off-topic responses in real time. Learn the main types and how to add them.
Jeffrey Ip
OWASP Top 10 2025 for LLM Applications: What’s new? Risks, and Mitigation Techniques
The 2025 OWASP Top 10 for LLM applications ranks risks from prompt injection to sensitive data disclosure. See what changed this year and how to mitigate each one.